Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2449. Min Act: 0.0000

Data Index: 1026258 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1170061 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2381. Min Act: -0.0000

Data Index: 578246 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2308. Min Act: -0.0000

Data Index: 941903 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2249. Min Act: 0.0001

Data Index: 705327 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2302. Min Act: -0.0001

Data Index: 433291 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2217. Min Act: 0.0000

Data Index: 26909 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2135. Min Act: -0.0000

Data Index: 65957 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2086. Min Act: -0.0001

Data Index: 205957 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2102. Min Act: -0.0000

Data Index: 60071 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2100. Min Act: -0.0000

Data Index: 533412 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1040470 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2038. Min Act: -0.0000

Data Index: 111983 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2046. Min Act: -0.0000

Data Index: 74154 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2023. Min Act: 0.0000

Data Index: 234164 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2229. Min Act: 0.0001

Data Index: 435163 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2070. Min Act: 0.0000

Data Index: 743622 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.2051. Min Act: -0.0000

Data Index: 180806 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1930. Min Act: -0.0001

Data Index: 61667 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.2490. Min Range: -0.2490

Max Act: 0.1972. Min Act: -0.0000

Data Index: 28495 (C4 (Web Text))

Max Activating Token Index: 719